Deep Neural Architectures for Mapping Scalp to Intracranial EEG
- Submitting institution
-
Royal Holloway and Bedford New College
- Unit of assessment
- 12 - Engineering
- Output identifier
- 39530589
- Type
- D - Journal article
- DOI
-
10.1142/S0129065718500090
- Title of journal
- International Journal of Neural Systems
- Article number
- 1850009
- First page
- 1
- Volume
- 28
- Issue
- 8
- ISSN
- 1793-6462
- Open access status
- Technical exception
- Month of publication
- April
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
6
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work is to enable the first machine learning algorithm to detect interictal epileptiform discharges (IEDs) from scalp EEG. This research was only possible, due to a unique dataset. The uniqueness of this dataset lies in the *pairing* between intracranial and scalp electroencephalogram (EEG). Less than 22% of those IEDs can be detected from scalp EEG, even by world leading neurologists. This paves the way for epileptic seizure prediction which reduces the anticonvulsant intake and mitigates the need for brain surgery.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
